ml-savitzky-golay-generalized - npm Package Compare versions

Comparing version 1.0.3 to 1.1.0

package.json

		{
		"name": "ml-savitzky-golay-generalized",
		"version": "1.0.3",
		"version": "1.1.0",
		"description": "Savitzky–Golay filter in Javascript",
		@@ -5,0 +5,0 @@ "main": "src/index.js",

README.md

		@@ -8,3 +8,24 @@ # savitzky-golay-generalized
		I'll try an automatic parameter tunning based on the SNR or in the entropy of the signal.
		#Usage
		```js
		npm i ml-savitzky-golay-generalized
		const SG = var SG = require("ml-savitzky-golay-generalized");
		SG(dataY, deltaX\|X, options)
		```
		##Parameters
		### dataY
		The data to be filtered.

		###deltaX \| X
		deltaX specifies the difference between 2 consecutive points of the independent: deltaX = X[i+1] - X[i]. Specficiying a deltaX suppose that all your points are equally spaced on the independent variable.
		If your points are not equally spaced in the ordinate variable, then you have to provide explicitelly your X values. The algorithm will use the average deltaX within each bin of 'windowSize' points to approximate the derivatives. This fast approximation only works if the X is almost locally equally spaced.

		###options
		####windowSize:
		The odd number of points to approximate the regresion polynomial. Default 9
		####derivative:
		The grade of the derivative. 0 by defualt(Smoothing)
		####polynomial:
		The order of the regresion polynomial. Default 3

		## Examples
		@@ -11,0 +32,0 @@

src/index.js

		@@ -6,5 +6,5 @@ //Code translate from Pascal source in http://pubs.acs.org/doi/pdf/10.1021/ac00205a007
		var defaultOptions = {
		windowSize: 11,
		windowSize: 9,
		derivative: 0,
		polynomial: 2,
		polynomial: 3,
		};
		@@ -11,0 +11,0 @@

New alerts